AI processors will lead the era of the Fourth Industrial Revolution
Artificial intelligence (AI) is one of the key emerging technologies. Global IT companies are competitively launching the newest technologies and competition is heating up more than ever. However, most AI technologies focus on software and their operating speeds are low, making them a poor fit for mobile devices. Therefore, many big companies are investing to develop semiconductor chips for running AI programs with low power requirements but at high speeds.
A research team led by Professor Hoi-Jun Yoo of the Department of Electrical Engineering has developed a semiconductor chip, CNNP (CNN Processor), that runs AI algorithms with ultra-low power, and K-Eye, a face recognition system using CNNP. The system was made in collaboration with a start-up company, UX Factory Co.
The K-Eye series consists of two types: a wearable type and a dongle type. The wearable type device can be used with a smartphone via Bluetooth, and it can operate for more than 24 hours with its internal battery. Users hanging K-Eye around their necks can conveniently check information about people by using their smartphone or smart watch, which connects K-Eye and allows users to access a database via their smart devices. A smartphone with K-EyeQ, the dongle type device, can recognize and share information about users at any time.
When recognizing that an authorized user is looking at its screen, the smartphone automatically turns on without a passcode, fingerprint, or iris authentication. Since it can distinguish whether an input face is coming from a saved photograph versus a real person, the smartphone cannot be tricked by the user’s photograph.
The K-Eye series carries other distinct features. It can detect a face at first and then recognize it, and it is possible to maintain “Always-on” status with low power consumption of less than 1mW. To accomplish this, the research team proposed two key technologies: an image sensor with “Always-on” face detection and the CNNP face recognition chip.
The first key technology, the “Always-on” image sensor, can determine if there is a face in its camera range. Then, it can capture frames and set the device to operate only when a face exists, reducing the standby power significantly. The face detection sensor combines analog and digital processing to reduce power consumption. With this approach, the analog processor, combined with the CMOS Image Sensor array, distinguishes the background area from the area likely to include a face, and the digital processor then detects the face only in the selected area. Hence, it becomes effective in terms of frame capture, face detection processing, and memory usage.
The second key technology, CNNP, achieved incredibly low power consumption by optimizing a convolutional neural network (CNN) in the areas of circuitry, architecture, and algorithms. First, the on-chip memory integrated in CNNP is specially designed to enable data to be read in a vertical direction as well as in a horizontal direction. Second, it has immense computational power with 1024 multipliers and accumulators operating in parallel and is capable of directly transferring the temporal results to each other without accessing to the external memory or on-chip communication network. Third, convolution calculations with a two-dimensional filter in the CNN algorithm are approximated into two sequential calculations of one-dimensional filters to achieve higher speeds and lower power consumption.
With these new technologies, CNNP achieved 97% high accuracy but consumed only 1/5000 power of the GPU. Face recognition can be performed with only 0.62mW of power consumption, and the chip can show higher performance than the GPU by using more power.
These chips were developed by Kyeongryeol Bong, a Ph. D. student under Professor Yoo and presented at the International Solid-State Circuit Conference (ISSCC) held in San Francisco in February. CNNP, which has the lowest reported power consumption in the world, has achieved a great deal of attention and has led to the development of the present K-Eye series for face recognition.
Professor Yoo said “AI – processors will lead the era of the Fourth Industrial Revolution. With the development of this AI chip, we expect Korea to take the lead in global AI technology.”
The Latest on: AI processor
Powering AI: The explosion of new AI hardware accelerators
on July 19, 2018 at 3:04 am
As noted in an Ars Technica article, today’s AI market has no hardware monoculture equivalent to Intel’s x86 CPU, which once dominated the desktop computing space. That’s because these new AI-accelera... […]
Huawei Announces Kirin 710, 12nm 64-bit Octa-Core Processor
on July 19, 2018 at 2:32 am
In addition to announcing this processor, Huawei also said that it will offer ‘AI photo features’ and ‘immersive gaming experience’, as it will feature an independent ISP and DSP, which was to be expe... […]
AI-based xPUs proliferating as new growth driver for IC supply chains
on July 19, 2018 at 12:22 am
With the advent of the 5G era, artificial intelligence (AI) applications will be in full swing, prompting chipmakers to develop multiple xPU chips beyond Intel's CPU and Nvidia's GPU solutions to supp... […]
Nokia X5 Has Finally Been Released – Comes With Dual 4G Voice over LTE (VoLTE) and Intelligent AI
on July 18, 2018 at 6:59 pm
The new Nokia X5 is equipped with the newly released Helio P60 processor in March 2018, 12nm low-power design, high-performance 8-core, built-in independent AI chip, and excellent GPU performance. It ... […]
Edge Computing Software Startup Swim.ai Scores $10M from VCs, Arm
on July 18, 2018 at 4:08 am
In addition to safety benefits, edge computing can also relieve bandwidth bottlenecks and reduce costs for moving masses of data to Web-based processors. Swim.ai has some hefty competitors in the edge ... […]
MediaTek Helio A22 to deliver AI features to mid-range
on July 17, 2018 at 7:59 pm
Often the preferred processor of Chinese brands and less expensive smartphones ... Qualcomm’s bottom line with its new Helio A series designed to bring camera and AI features to the budget smartphone ... […]
Stepping Out Of Science Fiction: A History Of Intel Powering AI
on July 17, 2018 at 2:12 pm
AI passed a major milestone in 1991 ... and by 2016 the Intel Xeon E5 family had become the most widely deployed processor for deep learning inference. The 22-core Xeon Broadwell E5 has 7.2 billion tr... […]
Samsung's 8Gb LPDDR5 chip wants to power future 5G and AI phones
on July 17, 2018 at 6:19 am
SAMSUNG WILL HELP shove artificial intelligence (AI) tech into more smartphones with its newly-minted ... to work more efficiently with the operating speed of the application processors it has been pa... […]
New eBOX560-900-FL AI System Features PCI Express Mini Card Slot for Wi-Fi and Bluetooth Connectivity
on July 17, 2018 at 4:16 am
Operated in -10°C to 50°C temperature range, eBOX560-900-FL is suitable for AI computing, deep learning ... a NVIDIA Jetson™ TX2 module which has a powerful 64-bit ARM A57 processor; a 256 CUDA cores ... […]
This AI Startup Could Be The Next DeepMind
on July 15, 2018 at 11:33 pm
Our dogged personification of AI as being humanlike is one of the reasons it has become ... or “edge computing,” in which cheap smartphone processors are finding their way into devices in the field to ... […]
via Google News and Bing News